Ollama API

https://docs.ollama.com/api/
Admin
Ollama's API allows developers to programmatically run and interact with large language models,...
Tokens:33,184
Snippets:191
Trust Score:9.9
Update:2 weeks ago
Show doc for...
Tokens:
Raw
### Example response from /api/show

Source: https://docs.ollama.com/api-reference/show-model-details

Example JSON response returned by the /api/show endpoint for the gemma4 model. It includes parameters, license, capabilities, thinking settings, and model details such as architecture and tokenizer configuration.

```json
{
  "parameters": "temperature 0.7\nnum_ctx 2048",
  "license": "Gemma Terms of Use \n\nLast modified: February 21, 2024...",
  "capabilities": [
    "completion",
    "thinking",
    "vision"
  ],
  "thinking": {
    "values": [
      false,
      true
    ],
    "default": true
  },
  "modified_at": "2025-08-14T15:49:43.634137516-07:00",
  "details": {
    "parent_model": "",
    "format": "gguf",
    "family": "gemma4",
    "families": [
      "gemma4"
    ],
    "parameter_size": "8.0B",
    "quantization_level": "Q4_K_M"
  },
  "model_info": {
    "gemma4.attention.head_count": 8,
    "gemma4.attention.head_count_kv": 2,
    "gemma4.attention.key_length": 512,
    "gemma4.attention.key_length_swa": 256,
    "gemma4.attention.layer_norm_rms_epsilon": 0.000001,
    "gemma4.attention.shared_kv_layers": 18,
    "gemma4.attention.sliding_window": 512,
    "gemma4.attention.value_length": 512,
    "gemma4.attention.value_length_swa": 256,
    "gemma4.audio.attention.head_count": 8,
    "gemma4.audio.attention.layer_norm_epsilon": 0.000001,
    "gemma4.audio.block_count": 12,
    "gemma4.audio.conv_kernel_size": 5,
    "gemma4.audio.embedding_length": 1024,
    "gemma4.audio.feed_forward_length": 4096,
    "gemma4.block_count": 42,
    "gemma4.context_length": 131072,
    "gemma4.embedding_length": 2560,
    "gemma4.embedding_length_per_layer_input": 256,
    "gemma4.feed_forward_length": 10240,
    "gemma4.final_logit_softcapping": 30,
    "gemma4.rope.dimension_count": 512,
    "gemma4.rope.dimension_count_swa": 256,
    "gemma4.rope.freq_base": 1000000,
    "gemma4.rope.freq_base_swa": 10000,
    "gemma4.vision.attention.head_count": 12,
    "gemma4.vision.attention.layer_norm_epsilon": 0.000001,
    "gemma4.vision.block_count": 16,
    "gemma4.vision.embedding_length": 768,
    "gemma4.vision.feed_forward_length": 3072,
    "gemma4.vision.num_channels": 3,
    "gemma4.vision.patch_size": 16,
    "gemma4.vision.projector.scale_factor": 3,
    "general.architecture": "gemma4",
    "general.file_type": 15,
    "general.quantization_version": 2,
    "tokenizer.ggml.add_bos_token": false,
    "tokenizer.ggml.add_eos_token": false,
    "tokenizer.ggml.add_mask_token": false,
    "tokenizer.ggml.add_padding_token": false,
    "tokenizer.ggml.add_unknown_token": false,
    "tokenizer.ggml.bos_token_id": 2,
    "tokenizer.ggml.eos_token_id": 1,
    "tokenizer.ggml.eos_token_ids": [
      1,
      106,
      50
    ],
    "tokenizer.ggml.mask_token_id": 4,
    "tokenizer.ggml.merges": null,
    "tokenizer.ggml.model": "llama",
    "tokenizer.ggml.padding_token_id": 0,
    "tokenizer.ggml.pre": "gemma4",
    "tokenizer.ggml.scores": null,
    "tokenizer.ggml.token_type": null,
    "tokenizer.ggml.tokens": null,
    "tokenizer.ggml.unknown_token_id": 3
  }
}
```

--------------------------------

### Response for GET /api/version

Source: https://docs.ollama.com/api-reference/get-version

Example JSON response from the version endpoint, showing the version field with the value "0.12.6".

```json
{
  "version": "0.12.6"
}
```

--------------------------------

### 200 response for GET /api/ps

Source: https://docs.ollama.com/api/ps

Example JSON response from the GET /api/ps endpoint. The 'models' array contains objects with details such as name, size, digest, and context_length for each running model.

```json
{
  "models": [
    {
      "name": "gemma4",
      "model": "gemma4",
      "size": 6591830464,
      "digest": "c6eb396dbd5992bbe3f5cdb947e8bbc0ee413d7c17e2beaae69f5d569cf982eb",
      "details": {
        "parent_model": "",
        "format": "gguf",
        "family": "gemma4",
        "families": [
          "gemma4"
        ],
        "parameter_size": "8.0B",
        "quantization_level": "Q4_K_M"
      },
      "expires_at": "2025-10-17T16:47:07.93355-07:00",
      "size_vram": 5333539264,
      "context_length": 4096
    }
  ]
}
```

--------------------------------

### 200 response example

Source: https://docs.ollama.com/api/systemone

Example 200 response from the /v1/systemone endpoint. Contains the model name, answers keyed by question name, and token usage. Probabilities and confidence are rounded to four decimal places.

```json
{
  "model": "nimble",
  "answers": {
    "label": {
      "type": "choice",
      "choice": "bug",
      "probabilities": {
        "billing": 0.0125,
        "bug": 0.9781,
        "account": 0.0093
      },
      "confidence": 0.8906
    }
  },
  "usage": {
    "input_tokens": 174,
    "output_tokens": 1
  }
}
```

--------------------------------

### Example /api/generate response with usage metrics

Source: https://docs.ollama.com/api/usage

Example non-streaming response from the /api/generate endpoint. Shows the usage metrics fields (total_duration, load_duration, prompt_eval_count, prompt_eval_cached_count, prompt_eval_duration, eval_count, eval_duration) and their values. All timing values are in nanoseconds.

```json
{
  "model": "gemma4",
  "created_at": "2025-10-17T23:14:07.414671Z",
  "response": "Hello! How can I help you today?",
  "done": true,
  "done_reason": "stop",
  "total_duration": 174560334,
  "load_duration": 101397084,
  "prompt_eval_count": 11,
  "prompt_eval_cached_count": 8,
  "prompt_eval_duration": 13074791,
  "eval_count": 18,
  "eval_duration": 52479709
}
```

--------------------------------

### Simple /v1/chat/completions example (curl)

Source: https://docs.ollama.com/api/openai-compatibility?utm_source=chatgpt.com

Sends a POST request to localhost:11434/v1/chat/completions with model gpt-oss:20b.

```curl
curl -X POST http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
  "model": "gpt-oss:20b",
  "messages": [{ "role": "user", "content": "Say this is a test" }]
}'

```

--------------------------------

### List models response (200)

Source: https://docs.ollama.com/api/tags

Example JSON response from the GET /api/tags endpoint, showing a model named 'gemma4' with its metadata.

```json
{
  "models": [
    {
      "name": "gemma4",
      "model": "gemma4",
      "modified_at": "2025-10-03T23:34:03.409490317-07:00",
      "size": 9608350245,
      "digest": "c6eb396dbd5992bbe3f5cdb947e8bbc0ee413d7c17e2beaae69f5d569cf982eb",
      "details": {
        "format": "gguf",
        "family": "gemma4",
        "families": [
          "gemma4"
        ],
        "parameter_size": "8.0B",
        "quantization_level": "Q4_K_M"
      }
    }
  ]
}
```

--------------------------------

### Simple /v1/responses example (JavaScript)

Source: https://docs.ollama.com/api/openai-compatibility?utm_source=chatgpt.com

Connects to local Ollama server at localhost:11434/v1. API key is required but ignored. Uses model qwen3:8b.

```JavaScript
import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "http://localhost:11434/v1/",
  apiKey: "ollama", // required but ignored
});

const responsesResult = await openai.responses.create({
  model: "qwen3:8b",
  input: "Write a short poem about the color blue",
});

console.log(responsesResult.output_text);

```

--------------------------------

### Simple /v1/chat/completions example (Python)

Source: https://docs.ollama.com/api/openai-compatibility?utm_source=chatgpt.com

Connects to local Ollama server at localhost:11434/v1. API key is required but ignored. Uses model gpt-oss:20b.

```Python
from openai import OpenAI

client = OpenAI(
    base_url='http://localhost:11434/v1/',
    api_key='ollama',  # required but ignored
)

chat_completion = client.chat.completions.create(
    messages=[
        {
            'role': 'user',
            'content': 'Say this is a test',
        }
    ],
    model='gpt-oss:20b',
)
print(chat_completion.choices[0].message.content)

```

--------------------------------

### Simple /v1/responses example (Python)

Source: https://docs.ollama.com/api/openai-compatibility?utm_source=chatgpt.com

Connects to local Ollama server at localhost:11434/v1. API key is required but ignored. Uses model qwen3:8b.

```Python
from openai import OpenAI

client = OpenAI(
    base_url='http://localhost:11434/v1/',
    api_key='ollama',  # required but ignored
)

responses_result = client.responses.create(
  model='qwen3:8b',
  input='Write a short poem about the color blue',
)
print(responses_result.output_text)

```

--------------------------------

### Simple /v1/responses example (curl)

Source: https://docs.ollama.com/api/openai-compatibility?utm_source=chatgpt.com

Sends a POST request to localhost:11434/v1/responses with model qwen3:8b.

```curl
curl -X POST http://localhost:11434/v1/responses \
-H "Content-Type: application/json" \
-d '{
  "model": "qwen3:8b",
  "input": "Write a short poem about the color blue"
}'

```

--------------------------------

### Streaming example in Python

Source: https://docs.ollama.com/api/anthropic-compatibility

Use the Anthropic Python SDK to stream a response from a local Ollama server. Prints text as it arrives.

```python
import anthropic

client = anthropic.Anthropic(
    base_url='http://localhost:11434',
    api_key='ollama',
)

with client.messages.stream(
    model='qwen3-coder',
    max_tokens=1024,
    messages=[{'role': 'user', 'content': 'Count from 1 to 10'}]
) as stream:
    for text in stream.text_stream:
        print(text, end='', flush=True)

```

--------------------------------

### Simple /v1/chat/completions example (JavaScript)

Source: https://docs.ollama.com/api/openai-compatibility?utm_source=chatgpt.com

Connects to local Ollama server at localhost:11434/v1. API key is required but ignored. Uses model gpt-oss:20b.

```JavaScript
import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "http://localhost:11434/v1/",
  apiKey: "ollama", // required but ignored
});

const chatCompletion = await openai.chat.completions.create({
  messages: [{ role: "user", content: "Say this is a test" }],
  model: "gpt-oss:20b",
});

console.log(chatCompletion.choices[0].message.content);

```

--------------------------------

### GET /api/ps

Source: https://docs.ollama.com/api/ps

Lists models currently loaded into memory.

```APIDOC
## [GET] /api/ps

### Description
Lists models currently loaded into memory.

### Method
GET

### Endpoint
/api/ps

### Response
#### Success Response (200)
- **models** (object[]) - Currently running models

#### Response Example
{
  "models": [
    {
      "name": "gemma4",
      "model": "gemma4",
      "size": 6591830464,
      "digest": "c6eb396dbd5992bbe3f5cdb947e8bbc0ee413d7c17e2beaae69f5d569cf982eb",
      "details": {
        "parent_model": "",
        "format": "gguf",
        "family": "gemma4",
        "families": [
          "gemma4"
        ],
        "parameter_size": "8.0B",
        "quantization_level": "Q4_K_M"
      },
      "expires_at": "2025-10-17T16:47:07.93355-07:00",
      "size_vram": 5333539264,
      "context_length": 4096
    }
  ]
}
```

--------------------------------

### Streaming example with curl

Source: https://docs.ollama.com/api/anthropic-compatibility

Send a streaming request to the local Ollama server using curl with stream: true.

```bash
curl -X POST http://localhost:11434/v1/messages \
-H "Content-Type: application/json" \
-d '{
  "model": "qwen3-coder",
  "max_tokens": 1024,
  "stream": true,
  "messages": [{ "role": "user", "content": "Count from 1 to 10" }]
}'

```

--------------------------------

### Simple /v1/messages example with curl

Source: https://docs.ollama.com/api/anthropic-compatibility

Send a message to the local Ollama server using curl with x-api-key header.

```bash
curl -X POST http://localhost:11434/v1/messages \
-H "Content-Type: application/json" \
-H "x-api-key: ollama" \
-H "anthropic-version: 2023-06-01" \
-d '{
  "model": "qwen3-coder",
  "max_tokens": 1024,
  "messages": [{ "role": "user", "content": "Hello, how are you?" }]
}'

```

--------------------------------

### /v1/chat/completions with vision example (Python)

Source: https://docs.ollama.com/api/openai-compatibility?utm_source=chatgpt.com

Connects to local Ollama server at localhost:11434/v1. API key is required but ignored. Uses model qwen3-vl:8b and includes an image_url content part.

```Python
from openai import OpenAI

client = OpenAI(
    base_url='http://localhost:11434/v1/',
    api_key='ollama',  # required but ignored
)

response = client.chat.completions.create(
    model='qwen3-vl:8b',
    messages=[
        {
            'role': 'user',
            'content': [
                {'type': 'text', 'text': "What's in this image?"},
                {
                    'type': 'image_url',

```

--------------------------------

### Simple /v1/messages example in Python

Source: https://docs.ollama.com/api/anthropic-compatibility

Use the Anthropic Python SDK to send a message to a local Ollama server. The api_key is required but ignored.

```python
import anthropic

client = anthropic.Anthropic(
    base_url='http://localhost:11434',
    api_key='ollama',  # required but ignored
)

message = client.messages.create(
    model='qwen3-coder',
    max_tokens=1024,
    messages=[
        {'role': 'user', 'content': 'Hello, how are you?'}
    ]
)
print(message.content[0].text)

```

--------------------------------

### Direct cloud access: chat completions with OpenAI client

Source: https://docs.ollama.com/api/openai-compatibility?utm_source=chatgpt.com

Set OLLAMA_API_KEY and install openai. Uses base_url https://ollama.com/v1 and model gemma4:31b.

```Python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://ollama.com/v1",
    api_key=os.environ["OLLAMA_API_KEY"],
)

response = client.chat.completions.create(
    model="gemma4:31b",
    messages=[{"role": "user", "content": "Say hello in one sentence."}],
)
print(response.choices[0].message.content)

```

--------------------------------

### Simple /v1/messages example in JavaScript

Source: https://docs.ollama.com/api/anthropic-compatibility

Use the Anthropic TypeScript SDK to send a message to a local Ollama server. The apiKey is required but ignored.

```javascript
import Anthropic from "@anthropic-ai/sdk";

const anthropic = new Anthropic({
  baseURL: "http://localhost:11434",
  apiKey: "ollama", // required but ignored
});

const message = await anthropic.messages.create({
  model: "qwen3-coder",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello, how are you?" }],
});

console.log(message.content[0].text);

```

--------------------------------

### Streamed response example (NDJSON)

Source: https://docs.ollama.com/api/streaming

Example of a streamed response from an endpoint like /api/generate, returned as newline-delimited JSON (application/x-ndjson). Each line is a separate JSON object with fields like model, created_at, response, and done. The final line includes done:true and done_reason.

```json
{"model":"gemma4","created_at":"2025-10-26T17:15:24.097767Z","response":"That","done":false}
{"model":"gemma4","created_at":"2025-10-26T17:15:24.109172Z","response":"'","done":false}
{"model":"gemma4","created_at":"2025-10-26T17:15:24.121485Z","response":"s","done":false}
{"model":"gemma4","created_at":"2025-10-26T17:15:24.132802Z","response":" a","done":false}
{"model":"gemma4","created_at":"2025-10-26T17:15:24.143931Z","response":" fantastic","done":false}
{"model":"gemma4","created_at":"2025-10-26T17:15:24.155176Z","response":" question","done":false}
{"model":"gemma4","created_at":"2025-10-26T17:15:24.166576Z","response":"!","done":true, "done_reason": "stop"}

```

--------------------------------

### GET /v1/models

Source: https://docs.ollama.com/api/openai-compatibility

Documentation for the /v1/models endpoint, which lists available models.

```APIDOC
## GET /v1/models

### Description
Lists the models available in the Ollama instance. The `created` field corresponds to when the model was last modified, and `owned_by` corresponds to the ollama username, defaulting to `"library"`.

### Method
GET

### Endpoint
/v1/models

### Response
#### Success Response (200)
- **object** (string) - Object type, e.g., "list".
- **data** (array) - List of model objects.

#### Response Example
{
  "object": "list",
  "data": [
    {
      "id": "model-id",
      "object": "model",
      "created": 1677610602,
      "owned_by": "library"
    }
  ]
}
```

--------------------------------

### Streaming example in JavaScript

Source: https://docs.ollama.com/api/anthropic-compatibility

Use the Anthropic TypeScript SDK to stream a response from a local Ollama server. Handles content_block_delta events.

```javascript
import Anthropic from "@anthropic-ai/sdk";

const anthropic = new Anthropic({
  baseURL: "http://localhost:11434",
  apiKey: "ollama",
});

const stream = await anthropic.messages.stream({
  model: "qwen3-coder",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Count from 1 to 10" }],
});

for await (const event of stream) {
  if (
    event.type === "content_block_delta" &&
    event.delta.type === "text_delta"
  ) {
    process.stdout.write(event.delta.text);
  }
}

```

--------------------------------

### GET /v1/models/{model}

Source: https://docs.ollama.com/api/openai-compatibility

Documentation for the /v1/models/{model} endpoint, which retrieves details about a specific model.

```APIDOC
## GET /v1/models/{model}

### Description
Retrieves information about a specific model. The `created` field corresponds to when the model was last modified, and `owned_by` corresponds to the ollama username, defaulting to `"library"`.

### Method
GET

### Endpoint
/v1/models/{model}

### Parameters
#### Path Parameters
- **model** (string) - Required - The model name.

### Response
#### Success Response (200)
- **id** (string) - Model identifier.
- **object** (string) - Object type, e.g., "model".
- **created** (integer) - Unix timestamp of last modification.
- **owned_by** (string) - Owner of the model.

#### Response Example
{
  "id": "model-id",
  "object": "model",
  "created": 1677610602,
  "owned_by": "library"
}
```

--------------------------------

### cURL request to list running models

Source: https://docs.ollama.com/api/ps

Use this cURL command to call the GET /api/ps endpoint. It returns a JSON response with an array of models currently loaded into memory.

```bash
curl http://localhost:11434/api/ps
```

--------------------------------

### Response from /api/embed

Source: https://docs.ollama.com/api/embed

Example JSON response showing the generated embeddings array and timing metrics. The response includes the model name, embeddings, total_duration, load_duration, and prompt_eval_count.

```json
{
  "model": "embeddinggemma",
  "embeddings": [
    [
      0.010071029,
      -0.0017594862,
      0.05007221,
      0.04692972,
      0.054916814,
      0.008599704,
      0.105441414,
      -0.025878139,
      0.12958129,
      0.031952348
    ]
  ],
  "total_duration": 14143917,
  "load_duration": 1019500,
  "prompt_eval_count": 8
}
```

--------------------------------

### cURL request to GET /api/version

Source: https://docs.ollama.com/api-reference/get-version

Sends a GET request to the Ollama API to retrieve the server version. The response is a JSON object containing the version string.

```bash
curl http://localhost:11434/api/version
```

--------------------------------

### POST /api/generate

Source: https://docs.ollama.com/api/generate

Documentation for the POST /api/generate endpoint, which generates a response from a model based on a prompt. It includes request body parameters, a cURL example, and the response schema with a 200 status code example.

```APIDOC
## [POST] /api/generate

### Description
Generates a response from a model based on a prompt. This endpoint accepts a model name and prompt, and returns the generated text along with metadata about the generation process.

### Method
POST

### Endpoint
/api/generate

### Parameters
#### Request Body
- **model** (string) - Required - Model name
- **prompt** (string) - Text for the model to generate a response from
- **suffix** (string) - Used for fill-in-the-middle models, text that appears after the user prompt and before the model response
- **images** (string[]) - Base64-encoded images for models that support image input
- **format** (string|object) - Structured output format for the model to generate a response from. Supports either the string `"json"` or a JSON schema object.
- **system** (string) - System prompt for the model to generate a response from
- **stream** (boolean) - default:true - When true, returns a stream of partial responses
- **think** (boolean|string) - Controls a model's thinking output. Use `/api/show` to discover the supported values and default for the selected model. `true` requests thinking, `false` requests no thinking output, and `null` uses the model default. String values are model-defined; supported names must match `/api/show` exactly. Numbers are not supported.
- **raw** (boolean) - When true, returns the raw response from the model without any prompt templating
- **keep_alive** (string|number) - Model keep-alive duration (for example `5m` or `0` to unload immediately)
- **options** (object) - Runtime options that control text generation
- **logprobs** (boolean) - Whether to return log probabilities of the output tokens
- **top_logprobs** (integer) - Number of most likely tokens to return at each token position when logprobs are enabled

### Request Example
```
curl http://localhost:11434/api/generate -d '{
  "model": "gemma4",
  "prompt": "Why is the sky blue?"
}'
```

### Response
#### Success Response (200)
- **model** (string) - Model name
- **created_at** (string) - ISO 8601 timestamp of response creation
- **response** (string) - The model's generated text response
- **thinking** (string) - The model's generated thinking output
- **done** (boolean) - Indicates whether generation has finished
- **done_reason** (string) - Reason the generation stopped
- **total_duration** (integer) - Time spent generating the response in nanoseconds
- **load_duration** (integer) - Time spent loading the model in nanoseconds
- **prompt_eval_count** (integer) - Number of input tokens in the prompt
- **prompt_eval_cached_count** (integer) - Number of prompt tokens read from the cache
- **prompt_eval_duration** (integer) - Time spent evaluating uncached prompt tokens in nanoseconds
- **eval_count** (integer) - Number of output tokens generated in the response
- **eval_duration** (integer) - Time spent generating tokens in nanoseconds
- **logprobs** (object[]) - Log probability information for the generated tokens when logprobs are enabled

#### Response Example
```
{
  "model": "<string>",
  "created_at": "<string>",
  "response": "<string>",
  "thinking": "<string>",
  "done": true,
  "done_reason": "<string>",
  "total_duration": 123,
  "load_duration": 123,
  "prompt_eval_count": 123,
  "prompt_eval_cached_count": 123,
  "prompt_eval_duration": 123,
  "eval_count": 123,
  "eval_duration": 123,
  "logprobs": [
    {
      "token": "<string>",
      "logprob": 123,
      "bytes": [
        123
      ],
      "top_logprobs": [
        {
          "token": "<string>",
          "logprob": 123,
          "bytes": [
            123
          ]
        }
      ]
    }
  ]
}
```
```

--------------------------------

### Non-streaming response example (JSON)

Source: https://docs.ollama.com/api/streaming

Example of a non-streaming response when streaming is disabled with {"stream": false}. The response is a single JSON object in application/json format, containing the full response text and done:true.

```json
{"model":"gemma4","created_at":"2025-10-26T17:15:24.166576Z","response":"That's a fantastic question!","done":true}

```

--------------------------------

### Run cloud model with ollama run

Source: https://docs.ollama.com/api/authentication

Runs a cloud model after signing in; authentication is handled automatically by Ollama.

```bash
ollama run gpt-oss:120b-cloud

```

--------------------------------

### GET /api/version

Source: https://docs.ollama.com/api-reference/get-version

Retrieves the version of the Ollama server. This endpoint returns a JSON object with the version string.

```APIDOC
## GET /api/version

### Description
Retrieves the version of the Ollama server.

### Method
GET

### Endpoint
/api/version

### Response
#### Success Response (200)
- **version** (string) - Version of Ollama

#### Response Example
{
  "version": "0.12.6"
}

```

--------------------------------

### List models with cURL

Source: https://docs.ollama.com/api/tags

Use this cURL command to retrieve the list of models from the local Ollama server. The endpoint is GET /api/tags.

```bash
curl http://localhost:11434/api/tags
```

--------------------------------

### Send chat completion with image to Ollama using OpenAI client

Source: https://docs.ollama.com/api/openai-compatibility?utm_source=chatgpt.com

Initializes the OpenAI client to point at a local Ollama server (baseURL http://localhost:11434/v1/) and sends a chat completion request with a text and image_url message to the qwen3-vl:8b model. The apiKey is required but ignored by Ollama.

```javascript
import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "http://localhost:11434/v1/",
  apiKey: "ollama", // required but ignored
});

const response = await openai.chat.completions.create({
  model: "qwen3-vl:8b",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "What's in this image?" },
        {
          type: "image_url",
          image_url:
```

--------------------------------

### 400 error response

Source: https://docs.ollama.com/api/systemone

Example error response body for the 400 status code. The error field contains a string describing the failure.

```json
{
  "error": "<string>"
}
```

--------------------------------

### POST /v1/completions

Source: https://docs.ollama.com/api/openai-compatibility?utm_source=chatgpt.com

Creates a completion for the provided prompt and parameters. Supports completions, streaming, JSON mode, reproducible outputs, and logprobs.

```APIDOC
## POST /v1/completions

### Description
Creates a completion for the provided prompt and parameters. Supports completions, streaming, JSON mode, reproducible outputs, and logprobs.

### Method
POST

### Endpoint
/v1/completions

### Parameters
#### Request Body
- **model** (string) - Required - The model name.
- **prompt** (string) - Required - The prompt to generate completions for. Currently only accepts a string.
- **frequency_penalty** (number) - Optional - Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency.
- **presence_penalty** (number) - Optional - Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far.
- **seed** (integer) - Optional - Seed for reproducible outputs.
- **stop** (string/array) - Optional - Up to 4 sequences where the API will stop generating further tokens.
- **stream** (boolean) - Optional - Whether to stream the response.
- **stream_options** (object) - Optional - Options for streaming.
  - **include_usage** (boolean) - Optional - Include usage information in the stream.
- **temperature** (number) - Optional - Sampling temperature.
- **top_p** (number) - Optional - Nucleus sampling parameter.
- **max_tokens** (integer) - Optional - Maximum number of tokens to generate.
- **suffix** (string) - Optional - The suffix that comes after a completion of inserted text.
- **best_of** (integer) - Optional - Generates best_of completions server-side and returns the "best".
- **echo** (boolean) - Optional - Echo back the prompt in addition to the completion.
- **logit_bias** (object) - Optional - Modifies the likelihood of specified tokens.
- **user** (string) - Optional - A unique identifier representing the end-user.
- **n** (integer) - Optional - Number of completions to generate.

### Response
#### Success Response (200)
- **id** (string) - The completion ID.
- **object** (string) - The object type.
- **created** (integer) - The creation timestamp.
- **model** (string) - The model used.
- **choices** (array) - The list of completion choices.
- **usage** (object) - Usage statistics.

#### Response Example
{
  "id": "cmpl-123",
  "object": "text_completion",
  "created": 1589478378,
  "model": "gpt-3.5-turbo-instruct",
  "choices": [
    {
      "text": "\n\nThis is a test.",
      "index": 0,
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 7,
    "total_tokens": 12
  }
}
```

--------------------------------

### POST /api/show

Source: https://docs.ollama.com/api-reference/show-model-details

Shows information about a model including details, license, and parameters.

```APIDOC
## POST /api/show

### Description
Shows information about a model including details, license, and parameters.

### Method
POST

### Endpoint
/api/show

### Parameters
#### Body
- **model** (string) - Required - Model name to show
- **verbose** (boolean) - Optional - If true, includes large verbose fields in the response.

### Request Example
```
curl http://localhost:11434/api/show -d '{
  "model": "gemma4"
}'
```

### Response
#### Success Response (200)
- **parameters** (string) - Model parameters
- **license** (string) - Model license
- **capabilities** (array) - Model capabilities
- **thinking** (object) - Thinking configuration
- **modified_at** (string) - Last modified timestamp
- **details** (object) - Model details
- **model_info** (object) - Model metadata

#### Response Example
```
{
  "parameters": "temperature 0.7\nnum_ctx 2048",
  "license": "Gemma Terms of Use \n\nLast modified: February 21, 2024...",
  "capabilities": [
    "completion",
    "thinking",
    "vision"
  ],
  "thinking": {
    "values": [
      false,
      true
    ],
    "default": true
  },
  "modified_at": "2025-08-14T15:49:43.634137516-07:00",
  "details": {
    "parent_model": "",
    "format": "gguf",
    "family": "gemma4",
    "families": [
      "gemma4"
    ],
    "parameter_size": "8.0B",
    "quantization_level": "Q4_K_M"
  },
  "model_info": {
    "gemma4.attention.head_count": 8,
    "gemma4.attention.head_count_kv": 2,
    "gemma4.attention.key_length": 512,
    "gemma4.attention.key_length_swa": 256,
    "gemma4.attention.layer_norm_rms_epsilon": 0.000001,
    "gemma4.attention.shared_kv_layers": 18,
    "gemma4.attention.sliding_window": 512,
    "gemma4.attention.value_length": 512,
    "gemma4.attention.value_length_swa": 256,
    "gemma4.audio.attention.head_count": 8,
    "gemma4.audio.attention.layer_norm_epsilon": 0.000001,
    "gemma4.audio.block_count": 12,
    "gemma4.audio.conv_kernel_size": 5,
    "gemma4.audio.embedding_length": 1024,
    "gemma4.audio.feed_forward_length": 4096,
    "gemma4.block_count": 42,
    "gemma4.context_length": 131072,
    "gemma4.embedding_length": 2560,
    "gemma4.embedding_length_per_layer_input": 256,
    "gemma4.feed_forward_length": 10240,
    "gemma4.final_logit_softcapping": 30,
    "gemma4.rope.dimension_count": 512,
    "gemma4.rope.dimension_count_swa": 256,
    "gemma4.rope.freq_base": 1000000,
    "gemma4.rope.freq_base_swa": 10000,
    "gemma4.vision.attention.head_count": 12,
    "gemma4.vision.attention.layer_norm_epsilon": 0.000001,
    "gemma4.vision.block_count": 16,
    "gemma4.vision.embedding_length": 768,
    "gemma4.vision.feed_forward_length": 3072,
    "gemma4.vision.num_channels": 3,
    "gemma4.vision.patch_size": 16,
    "gemma4.vision.projector.scale_factor": 3,
    "general.architecture": "gemma4",
    "general.file_type": 15,
    "general.quantization_version": 2,
    "tokenizer.ggml.add_bos_token": false,
    "tokenizer.ggml.add_eos_token": false,
    "tokenizer.ggml.add_mask_token": false,
    "tokenizer.ggml.add_padding_token": false,
    "tokenizer.ggml.add_unknown_token": false,
    "tokenizer.ggml.bos_token_id": 2,
    "tokenizer.ggml.eos_token_id": 1,
    "tokenizer.ggml.eos_token_ids": [
      1,
      106,
      50
    ],
    "tokenizer.ggml.mask_token_id": 4,
    "tokenizer.ggml.merges": null,
    "tokenizer.ggml.model": "llama",
    "tokenizer.ggml.padding_token_id": 0,
    "tokenizer.ggml.pre": "gemma4",
    "tokenizer.ggml.scores": null,
    "tokenizer.ggml.token_type": null,
    "tokenizer.ggml.tokens": null,
    "tokenizer.ggml.unknown_token_id": 3
  }
}
```
```

--------------------------------

### GET /api/tags

Source: https://docs.ollama.com/api/tags

Lists models that are available locally. Returns an array of model objects with details such as name, size, digest, and model details.

```APIDOC
## GET /api/tags

### Description
Lists models that are available locally.

### Method
GET

### Endpoint
/api/tags

### Response
#### Success Response (200)
- **models** (object[]) - List of model objects.
  - **name** (string) - Model name.
  - **model** (string) - Model identifier.
  - **modified_at** (string) - Last modified timestamp.
  - **size** (integer) - Model size in bytes.
  - **digest** (string) - Model digest.
  - **details** (object) - Model details.
    - **format** (string) - Model format (e.g., gguf).
    - **family** (string) - Model family.
    - **families** (string[]) - List of model families.
    - **parameter_size** (string) - Parameter size (e.g., 8.0B).
    - **quantization_level** (string) - Quantization level (e.g., Q4_K_M).

#### Response Example
{
  "models": [
    {
      "name": "gemma4",
      "model": "gemma4",
      "modified_at": "2025-10-03T23:34:03.409490317-07:00",
      "size": 9608350245,
      "digest": "c6eb396dbd5992bbe3f5cdb947e8bbc0ee413d7c17e2beaae69f5d569cf982eb",
      "details": {
        "format": "gguf",
        "family": "gemma4",
        "families": [
          "gemma4"
        ],
        "parameter_size": "8.0B",
        "quantization_level": "Q4_K_M"
      }
    }
  ]
}
```

--------------------------------

### POST /v1/systemone

Source: https://docs.ollama.com/api/systemone

Documentation for the POST /v1/systemone endpoint, including request body parameters, response schema, and error responses.

```APIDOC
## POST /v1/systemone

### Description
Processes a state with named questions and returns answers and token usage. This endpoint is available locally in Ollama and returns a single JSON response.

### Method
POST

### Endpoint
/v1/systemone

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
- **model** (string) - Required - Local model trained for System One, such as nimble. Requires compatible GGUF weights and a scoring-capable runner; cloud and MLX/Safetensors models are not supported. Pattern: `\S`
- **state** (string|object|any[]|string|object|any[]) - Required - A nonempty string, or an object or array serialized as JSON text. Not interpreted as chat messages or multimodal input. Pattern: `\S`
- **questions** (object) - Required - Named questions about the shared state. Answers are not passed to later questions.
- **images** (string<byte>[]) - Optional - Base64-encoded images shared by all questions, in request order. Requires Clef or Clef Flash with vision weights. URLs and data URLs are not supported.
- **keep_alive** (string|number|string|number) - Optional - How long to keep the model loaded after the request, as a duration string (such as 5m) or seconds. Zero unloads after the request; a negative value keeps it loaded. Defaults to the server's keep-alive setting (5m unless configured otherwise).

### Request Example
```json
{
  "model": "nimble",
  "state": "Our checkout has returned 500 errors since 9am.",
  "questions": {
    "label": {
      "type": "choice",
      "instructions": "Which label fits this ticket?",
      "criteria": {
        "billing": "Payments and refunds",
        "bug": "Software errors",
        "account": "Login and account access"
      }
    }
  }
}
```

### Response
#### Success Response (200)
- **model** (string) - Required - Model name from the request.
- **answers** (object) - Required - Answers keyed by the question names in the request.
- **usage** (object) - Required - Token usage details.

#### Response Example
```json
{
  "model": "nimble",
  "answers": {
    "label": {
      "type": "choice",
      "choice": "bug",
      "probabilities": {
        "billing": 0.0125,
        "bug": 0.9781,
        "account": 0.0093
      },
      "confidence": 0.8906
    }
  },
  "usage": {
    "input_tokens": 174,
    "output_tokens": 1
  }
}
```

#### Error Responses
- **400** - Bad Request - `{"error": "<string>"}`
- **404** - Not Found - `{"error": "<string>"}`
- **413** - Payload Too Large - `{"error": "request body must not exceed 64 KiB without images"}`
- **500** - Internal Server Error - `{"error": "<string>"}`
```
Tokens:
Raw